US4456955A - Alignment of one operand of a two operand arithmetic unit - Google Patents

Alignment of one operand of a two operand arithmetic unit Download PDF

Info

Publication number
US4456955A
US4456955A US06/294,053 US29405381A US4456955A US 4456955 A US4456955 A US 4456955A US 29405381 A US29405381 A US 29405381A US 4456955 A US4456955 A US 4456955A
Authority
US
United States
Prior art keywords
operand
means
indicating
byte
position
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Lifetime
Application number
US06/294,053
Inventor
Tomoatsu Yanagita
Motonobu Nagafuji
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hitachi Ltd
Original Assignee
Hitachi Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority to JP55118218A priority Critical patent/JPH028327B2/ja
Priority to JP55-118218 priority
Application filed by Hitachi Ltd filed Critical Hitachi Ltd
Assigned to HITACHI, LTD., 5-1, MARUNOUCHI 1-CHOME, CHUIODA-KU, TOKYO, JAPAN A CORP. OF JAPAN reassignment HITACHI, LTD., 5-1, MARUNOUCHI 1-CHOME, CHUIODA-KU, TOKYO, JAPAN A CORP. OF JAPAN ASSIGNMENT OF ASSIGNORS INTEREST. Assignors: NAGAFUJI, MOTONOBU, YANAGITA, TOMOATSU
Application granted granted Critical
Publication of US4456955A publication Critical patent/US4456955A/en
Anticipated expiration legal-status Critical
Application status is Expired - Lifetime legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/30003Arrangements for executing specific machine instructions
    • G06F9/30007Arrangements for executing specific machine instructions to perform operations on data operands
    • G06F9/3001Arithmetic instructions
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F7/00Methods or arrangements for processing data by operating upon the order or content of the data handled
    • G06F7/38Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation
    • G06F7/48Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation using non-contact-making devices, e.g. tube, solid state device; using unspecified devices
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F7/00Methods or arrangements for processing data by operating upon the order or content of the data handled
    • G06F7/38Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation
    • G06F7/48Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation using non-contact-making devices, e.g. tube, solid state device; using unspecified devices
    • G06F7/499Denomination or exception handling, e.g. rounding, overflow
    • G06F7/49936Normalisation mentioned as feature only

Abstract

A data processing system has an arithmetic operating unit to process a plurality of bytes at a time and carries out an arithmetic operation on first and second operands each starting from any desired address on a main memory and having any desired number of byte length. The second operand is aligned to an operand position of the first operand and the aligned second operand is supplied to the operating unit while the first operand is supplied as it is to the operating unit. Since the second operand is aligned to the operand position of the first operand before it is processed in the operating unit, the number of times of alignment is reduced.

Description

BACKGROUND OF THE INVENTION

1. Field of the Invention

The present invention relates to a data processing system, and more particularly to a data processing system which can reduce the total time of operation when first and second operands each starting at any desired address of a main memory and having any desired byte length are processed.

2. Description of the Prior Art

In a data processing system, when a variable operand length instruction, such as a decimal operation instruction, is to be processed, it may be processed byte by byte by a one-byte width adder or a plurality of bytes at a time by a four- or eight-byte width adder in order to process at a high speed.

The latter method can process faster that the former method because a plurality of bytes are processed at a time. However, the latter method still has a problem to be resolved in that much time is required to align the operand position. The latter method is more specifically described below. The first operand is shifted to align to a specified byte position. Then, the second operand is shifted to align to the same byte position as the first operand. The first and second operands are then processed. A result of the operation is shifted to align to the first operand position. Thus, three alignments of the operand position, that is, the shift of the first operand, the shift of the second operand and the shift of the operation result are required. As a result, the time required to perform the alignment of the operand position is long relative to the actual operation time and the instruction executive time is not shortened in spite of the provision of the wide width adder.

SUMMARY OF THE INVENTION

It is an object of the present invention to provide a data processing system which reduces the time required for the alignment of the operand position by reducing the number of times alignment is performed so that the execution performance for the instruction is enhanced.

In accordance with the present invention, the operation is carried out while the operand position of the second operand is aligned to the operand position of the first operand. By this method, the required number of times of alignment of the operand position is reduced to one.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 shows an example of a variable operand length instruction used to explain the invention.

FIG. 2 shows a prior art example for processing on the instruction of FIG. 1 a plurality of bytes at a time.

FIG. 3 illustrates an embodiment of the present invention, respectively.

FIG. 4 is a logic circuit diagram of the zero assurance circuits of FIG. 3.

FIG. 5 is a logic circuit diagram of one stage of the gate circuit 32 of FIG. 4.

FIG. 6 is a logic circuit diagram of one portion of the control circuit 31 of FIG. 4

FIG. 7 is a logic circuit diagram of another portion of the control circuit 31 of FIG. 4.

FIG. 8 is a logic circuit diagram of another portion of the control circuit 31 of FIG. 4.

FIG. 9 is a logic circuit diagram of another portion of the control circuit 31 of FIG. 4.

FIGS. 10A and 10B illustrate relations between input and output of the decoder shown in FIG. 6.

DESCRIPTION OF THE PREFERRED EMBODIMENTS

For the sake of convenience, an instruction as shown in FIG. 1 is considered as a variable operand length instruction in the following description. In FIG. 1, an OP field indicates a type of operation such as add, subtract, multiply or divide, L1 and L2 fields indicate the lengths in bytes of the first and second operands, respectively, and ADR1 and ADR2 fields indicate leading addresses in a main storage of the first and second operands, respectively. The L1 and L2 fields are assumed to have four bits, respectively. (Thus, a maximum operand length is 15 bytes). It is now assumed that the first operand having the length of L1 bytes from the address in the main memory indicated by the ADR1 field and the second operand having the length of L2 bytes from the address in the main memory indicated by the ADR2 field are added or subtracted with the right ends (trailing ends) of the operands being aligned, that is, each operand has a decimal point at a right end of the operand field and the result of this operation is stored in the first operand field in the main memory. It is also assumed that the data transfer between the processor and the main memory is effected eight bytes at a time.

In order to facilitate an understanding of the present invention, prior art examples are first explained with reference to FIG. 2.

FIG. 2 shows a prior art system which executes the instruction of FIG. 1 to process a plurality of bytes at a time by an eight-byte width adder, in which a five-byte first operand "abcde" from a byte position 1 in an eight-byte address boundary in a main memory and a three-byte second operand "lmn" from a byte position 2 in the eight-byte address boundary in the main memory are added together. The first operand (i) read from the main memory is shifted right by two bytes so that the right end thereof is aligned to a byte position 7 as shown in (iii). "0's" are inserted into the byte positions 0-2 on the left of the left end of the operand. The second operand (ii) read from the main memory is then shifted right by three bytes so that the right end thereof is aligned to the byte position 7, and "0's" are inserted into the byte positions 0-4 on the left of the left end of the operand, as shown in (iv). The operands (iii) and (iv) so aligned are applied to an adder to produce a sum (v). Finally, the sum is shifted left by two bytes to align it to the first operand position as shown in (vi) and the aligned sum is stored in the main memory.

As described above with reference to FIG. 2, the prior art systems for processing a plurality of bytes at a time need three alignments of the operand position, that is, the right shift of the first operand, the right shift of the second operand and the left shift of the operation result. As a result, the time required for the alignment of the operand position is long relative to the actual operation time and the instruction execution time is not shortened in spite of the provision of the wide width adder.

FIG. 3 shows a block diagram of one embodiment of the present invention, in which a five-byte first operand "abcde" from a byte position 1 in an eight-byte address boundary of a main memory and a three-byte second operand "lmn" from a byte position 2 in the eight-byte address boundary are added, like the example of FIG. 2. In FIG. 3, the first operand read from the main memory 9 is loaded into a register 11 while the second operand is loaded into a register 12. The instruction described above is set into an instruction register 10. The second operand in the register 12 is supplied to a shifter 14 where it is aligned with the operand position of the first operand and the aligned second operand is loaded into a register 15. That is, the second operand is shifted right by two bytes. The shifter 14 is a well-known one which is controlled by a shifter control circuit 13, which in turn is a well-known subtraction circuit to which the respective three low bits CNT1(0-2) and CNT2(0-2) of the leading addresses (right end addresses) of the first and second operands, respectively, indicated by the command are applied and which subtracts the three low bits CNT2(0-2) of the leading address of the second operand from the three low bits CNT1(0-2) of the leading address of the first operand. If a difference is positive, the shifter 14 shifts the second operand to the right by the number of bytes corresponding to the difference, and if the difference is negative, it shifts the second operand to the left by the number of bytes corresponding to the difference. In the example of FIG. 3, the second operand is shifted right by one byte so that the right end of the second operand is aligned to the right end of the first operand. The first operand in the register 11 is applied as it is to an adder 18 through a zero assurance circuit 16 to be described later and the second operand in the register 15, which has been aligned to the operand position of the first operand, is applied to the adder 18 through a zero assurance circuit 17 to be described later. The adder 18 adds the input first and second operands and a resulting sum is loaded into a register 19. The sum is in alignment with the operand position of the first operand and hence it may be stored as it is in the main memory.

In this manner, in accordance with the present invention, the number of times of the alignment of the operand position is reduced from three, which was necessary in the prior art system, to one, and the instruction execution performance is enhanced. In the operation in accordance with the present invention, a correct result could not be obtained if zeros were not assured in the byte positions on the right of the right ends of the first and second operands (that is, the byte positions 6 and 7 of the registers 11 and 15) and in the byte positions on the left of the left ends (that is, the byte position 0 of the register 11 and the byte positions 0-2 of the register 15) in the addition operation of FIG. 3. The high-speed zero assurance circuits 16 and 17 shown in FIG. 3 assure zeros in the ineffective positions of the first and second operands. The circuit 16 in FIG. 3 determines the ineffective positions of the first operand from the right end byte position of the first operand and the length of the first operand, and the circuit 17 in FIG. 3 determines the ineffective positions of the second operand from the right end byte position of the first operand and the length of the second operand, to assure zeros at those positions.

It is now assumed that the eight-byte position pointers CNT1(0), CNT1(1) and CNT1(2) contain the three lower bits of the right end address of the first operand respectively.

Table 1 shows ineffective byte positions on the right of the right end of the operand. For example, when CNT1(0-2) are "5", the byte positions 6 and 7 are ineffective bytes (for the first operand in the register 11 in FIG. 3).

              TABLE 1______________________________________Content of CNT1(0-2)0     1        2      3      4    5      6   7______________________________________1-7   2-7      3-7    4-7    5-7  6-7    7   --______________________________________

Table 2 shows the ineffective byte positions on the left of the left end of the operand. For example, when CNT1(0-2) are "5" and the operand length is five-byte length, the byte position 0 is the ineffective byte (for the first operand in the register 11 of FIG. 3).

              TABLE 2______________________________________OperandByte   Content of CNT1(0-2)Length 0      1      2    3     4    5    6     7______________________________________0      0      0-1    0-2  0-3   0-4  0-5  0-6   0-71      --     0      0-1  0-2   0-3  0-4  0-5   0-62      --     --     0    0-1   0-2  0-3  0-4   0-53      --     --     --   --    0-1  0-2  0-3   0-44      --     --     --   --    0    0-1  0-2   0-35      --     --     --   --    --   0    0-1   0-26      --     --     --   --    --   --   0     0-17      --     --     --   --    --   --   --    08 for  --     --     --   --    --   --   --    --longer______________________________________

The above indicates that the ineffective bytes of the second operand also can be determined from the three lower bits CNT1(0-2) at the right end address of the first operand and the second byte length of the operand.

Thus, by supplying the first and second operands which have been zero assured for the ineffective bytes shown in the Tables 1 and 2, to the arithmetic operation circuit, a correct operation result is obtained. Symbol "-" in Tables 1 and 2 indicates the absence of the ineffective byte.

Examples of the zero assurance circuits 16 and 17 shown in FIG. 3 are illustrated in FIG. 4, in which numeral 31 denotes a control circuit for the zero assurance circuit. It produces ineffective byte suppress signals 100-107 in response to inputs 150-152 and 170-173 in accordance with Tables 1 and 2. The inputs 150-152 indicate the right end byte position of the first operand, and the CNT1(0-2) are applied thereto. The inputs 170-173 indicate the operand length. The four bits in the L1 field in FIG. 1 are applied thereto in the assurance circuit 16 of FIG. 3, and the four bits in the L2 field in FIG. 1 are applied in the assurance circuit 17 of FIG. 3. While the zero assurance circuit 16 for the first operand in FIG. 3 is explained below, the zero assurance circuit 17 for the second operand in FIG. 3 is also similarly constructed.

Numeral 32 in FIG. 4 denotes an eight-byte width gate circuit which gates signals 300-363 of first operand inputs 200-263 supplied from the register 11 to the adder 18. The signal 300-363 have their ineffective bytes zero-assumed by control signals 100-107 to the 0-th to seventh bytes. The outputs 300-363 of the gate 32 are applied to first operand input terminals of the adder shown in FIG. 3. Numeral 40 denotes the 0-th byte of the gate circuit 32, which is shown in detail in FIG. 5. In FIG. 5, the eight-bit input data signals 200-207 to the 0-th byte are gated by the control signal 100 and the output data signals 300-307 are produced. When the 0-th byte is an ineffective byte and zeros are to be assured, the control signal 100 assumes a logical "1" and the output data signals 300-307 all assume "0's." When the control signal 100 is logical "0," the input data signals 200-207 are directly gated as the output data signals 300-307.

FIGS. 6 through 9 show examples of the control circuit 31 of FIG. 4.

In FIG. 6, a decoder DEC1 of the signals 150-152 indicating the right end byte position of the first operand, that is, CNT1(0-2), and a decoder DEC2 for the signals 170-173 indicating the byte length of the first operand, that is, the L1 field of the operand are shown. The relations between the inputs and the outputs of the decoders DEC1 and DEC2 are shown in FIGS. 10A and 10B.

FIG. 7 shows a logical circuit for determining the ineffective bytes on the left of the left end of the operand shown in Table 2. It responds to the decoder outputs 160-167 and 180-187 in FIG. 6 to produce the suppression signals 110-117 for the bytes 0-7.

FIG. 8 shows a logic circuit for determining the ineffective bytes on the right of the right end of the operand shown in Table 1, and it responds to the decoder outputs 160-166 in FIG. 6 to produce the suppression signals 121-127 for the bytes 1-7.

FIG. 9 shows OR circuits for the ineffective byte suppression signals 110-117 and 121-127 shown in FIGS. 7 and 8. The outputs 100-107 from the OR circuits serve as the suppression signals for the outputs of the control circuit of FIG. 4 or the input data for the 0-th to seventh bytes to the adder.

While the zero assurance circuit 16 for the first operand in FIG. 3 has been described, the zero assurance circuit 17 for the second operand in FIG. 3 can be similarly constructed.

The operation of the arithmetic unit having the zero assurance circuit is explained for a case where the operand crosses an eight-byte boundary. It is assumed that the right end byte of the first operand is at the byte position 4 within the eight-byte boundary and the first operand is of nine-byte length. The first operand is carried out with CNT1(0:2)=4 as described above and the fifth to seventh bytes of the inputs to the arithmetic unit are set to zero in accordance with Tables 1 and 2 and the result of operaion appears at 0th to fourth byte positions. After the completion of the first operation, CNT1(0-2) are set to "7" and the number of bytes processed in the first operation is subtracted from the operand length L1. In the present example, since five bytes have been processed in the first operation, the five bytes are subtracted from the nine bytes resulting in four remaining bytes. The final carry in the first operation is stored to use it as an initial carry in the second operation. In the second operation, since CNT1(0-2) are "7" as seen from Table 2 and the operand is of four-byte length, the bytes 0-3 of the inputs are rendered zero and the operation result appears at the byte positions 4-7. The operation results of the two operations are stored in the first operand address on the main memory.

The preferred embodiment of the present invention has thus been described. The present invention is also applicable to an operation instruction in which the left end position of the first operand in the main memory and the left end position of the second memory are aligned and the result of the operation is stored at the first operand position. The ineffective bytes on the right of the right end of the operand and the ineffective bytes on the left of the left end of the operand are shown in Tables 3 and 4. The circuits for assuring zeros for the ineffective bytes may be realized by substantially identical logic circuits to those shown in the above embodiments.

              TABLE 3______________________________________OperandByte   Content of CNT1(0-2)Length 0      1       2    3    4     5    6    7______________________________________0      0-7    1-7     2-7  3-7  4-7   5-7  6-7  71      1-7    2-7     3-7  4-7  5-7   6-7  7    --2      2-7    3-7     4-7  5-7  6-7   7    --   --3      3-7    4-7     5-7  6-7  7     --   --   --4      4-7    5-7     6-7  7    --    --   --   --5      5-7    6-7     7    --   --    --   --   --6      6-7    7       --   --   --    --   --   --7      7      --      --   --   --    --   --   --8 or   --     --      --   --   --    --   --   --longer______________________________________

              TABLE 4______________________________________Content of CNT1(0-2)0    1       2      3      4    5      6    7______________________________________--   0       0-1    0-2    0-3  0-4    0-5  0-6______________________________________

As is apparent from the description set forth above, the present invention can reduce the time required for the alignment of the operand position when the variable operand length instruction is processed a plurality of bytes at a time, and zeros are assured at a high speed for the ineffective bytes of the operand. Accordingly, the execution time of the instruction can be substantially reduced.

Claims (3)

What is claimed is:
1. A data processing system for processing first and second operands each starting from a designated address in a memory and having a designated number of bytes comprising:
designation means for designating leading addresses and the byte lengths representing the number of bytes of said first and second operands in said memory;
first and second hold means connected to said memory for holding said first and second operands read from said memory, respectively;
alignment means connected to said designation means and said second hold means for shifting the second operand supplied from said second hold means by an amount indicated by the leading addresses of the first and second operands designated by said designation means so as to align the operand position of said second operand with the operand position of said first operand;
first control means connected to said designation means for indicating ineffective byte positions in the first operand for arithmetic operation based on the leading address and the byte length of the first operand indicated in said designation means, said first control means including:
(a) first indicating means for indicating the byte position on the left of the left end of said first operand,
(b) second indicating means for indicating the byte position on the right of the right end of said first operand and,
(c) means connected to said first and second indicating means for indicating ineffective byte positions of said first operand for arithmetic operation in response to the indications of said first and second indicating means;
second control means connected to said designation means for indicating ineffective byte positions in the second operand for arithmetic operation based on the leading address of the first operand and the byte length of the second operand indicated by said designation means, said second control means including:
(a) third indicating means for indicating the byte position on the left of the left end of said second operand,
(b) fourth indicating means for indicating the byte position on the right of the right end of said second operand and,
(c) means connected with said third and fourth indicating means for indicating ineffective byte positions in said second operand for arithmetic operation in response to the indications of said third and fourth indicating means;
first gate means connected to said first hold means and said first control means for suppressing the ineffective byte positions of the first operand supplied from said first hold means in response to the indication from said first control means to thereby output the first operand;
second gate means connected to said alignment means and said second control means for suppressing the ineffective byte positions of the second operand supplied from said alignment means in response to the indication from said second control means to thereby output the second operand; and
arithmetic operation means connected to said first and second gate means for carrying out an arithmetic operation on the first and second operands supplied from said first and second gate means to produce an output of the result.
2. The data processing system according to claim 1, wherein said first indicating means is connected to receive signals representing the leading address and the length of said first operand, said second and fourth indicating means are connected to receive a signal representing the leading address of the first operand, and said third indicating means is connected to receive signals representing the leading address of the first operand and the length of the second operand.
3. The data processing system according to claim 2, wherein said first and second gate means include means for placing zero at suppressed byte positions.
US06/294,053 1980-08-27 1981-08-18 Alignment of one operand of a two operand arithmetic unit Expired - Lifetime US4456955A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP55118218A JPH028327B2 (en) 1980-08-27 1980-08-27
JP55-118218 1980-08-27

Publications (1)

Publication Number Publication Date
US4456955A true US4456955A (en) 1984-06-26

Family

ID=14731136

Family Applications (1)

Application Number Title Priority Date Filing Date
US06/294,053 Expired - Lifetime US4456955A (en) 1980-08-27 1981-08-18 Alignment of one operand of a two operand arithmetic unit

Country Status (3)

Country Link
US (1) US4456955A (en)
JP (1) JPH028327B2 (en)
KR (1) KR860000791B1 (en)

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0220684A2 (en) * 1985-10-25 1987-05-06 Hitachi, Ltd. Data processing system
EP0438961A2 (en) * 1990-01-24 1991-07-31 International Business Machines Corporation Hardware data string operation controller
EP0593073A1 (en) * 1992-10-16 1994-04-20 Matsushita Electric Industrial Co., Ltd. A processor incorporating shifters
US5367705A (en) * 1990-06-29 1994-11-22 Digital Equipment Corp. In-register data manipulation using data shift in reduced instruction set processor
US5438668A (en) * 1992-03-31 1995-08-01 Seiko Epson Corporation System and method for extraction, alignment and decoding of CISC instructions into a nano-instruction bucket for execution by a RISC computer
US5463746A (en) * 1992-10-30 1995-10-31 International Business Machines Corp. Data processing system having prediction by using an embedded guess bit of remapped and compressed opcodes
US5471598A (en) * 1993-10-18 1995-11-28 Cyrix Corporation Data dependency detection and handling in a microprocessor with write buffer
US5584009A (en) * 1993-10-18 1996-12-10 Cyrix Corporation System and method of retiring store data from a write buffer
US5615402A (en) * 1993-10-18 1997-03-25 Cyrix Corporation Unified write buffer having information identifying whether the address belongs to a first write operand or a second write operand having an extra wide latch
US5673216A (en) * 1995-12-19 1997-09-30 International Business Machines Corporation Process and system for adding or subtracting symbols in any base without converting to a common base
US5740398A (en) * 1993-10-18 1998-04-14 Cyrix Corporation Program order sequencing of data in a microprocessor with write buffer
US6219773B1 (en) * 1993-10-18 2001-04-17 Via-Cyrix, Inc. System and method of retiring misaligned write operands from a write buffer
US6230254B1 (en) 1992-09-29 2001-05-08 Seiko Epson Corporation System and method for handling load and/or store operators in a superscalar microprocessor
WO2002019093A1 (en) * 2000-08-31 2002-03-07 Intel Corporation Method and apparatus for flexible data types
US6434693B1 (en) 1992-09-29 2002-08-13 Seiko Epson Corporation System and method for handling load and/or store operations in a superscalar microprocessor
US20030225984A1 (en) * 2000-08-10 2003-12-04 Terminus Technology Limited Associative memory having a mask function for use in a network router
US20040236896A1 (en) * 2000-01-31 2004-11-25 Ruban Kanapathippillai Memory with memory clusters for power reduction in an integrated circuit
US20060047740A1 (en) * 2004-08-30 2006-03-02 Casio Computer Co., Ltd. Decimal computing apparatus, electronic device connectable decimal computing apparatus, arithmetic operation apparatus, arithmetic operation control apparatus, and program-recorded recording medium

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2504847B2 (en) * 1989-10-27 1996-06-05 甲府日本電気株式会社 10 Susumude - other check circuit
JPH04116717A (en) * 1990-09-07 1992-04-17 Koufu Nippon Denki Kk Overflow exception detection system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4135242A (en) * 1977-11-07 1979-01-16 Ncr Corporation Method and processor having bit-addressable scratch pad memory
US4189768A (en) * 1978-03-16 1980-02-19 International Business Machines Corporation Operand fetch control improvement
US4219874A (en) * 1978-03-17 1980-08-26 Gusev Valery Data processing device for variable length multibyte data fields
US4268909A (en) * 1979-01-02 1981-05-19 Honeywell Information Systems Inc. Numeric data fetch - alignment of data including scale factor difference
US4317170A (en) * 1979-01-19 1982-02-23 Hitachi, Ltd. Microinstruction controlled data processing system including micro-instructions with data align control feature

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4135242A (en) * 1977-11-07 1979-01-16 Ncr Corporation Method and processor having bit-addressable scratch pad memory
US4189768A (en) * 1978-03-16 1980-02-19 International Business Machines Corporation Operand fetch control improvement
US4219874A (en) * 1978-03-17 1980-08-26 Gusev Valery Data processing device for variable length multibyte data fields
US4268909A (en) * 1979-01-02 1981-05-19 Honeywell Information Systems Inc. Numeric data fetch - alignment of data including scale factor difference
US4317170A (en) * 1979-01-19 1982-02-23 Hitachi, Ltd. Microinstruction controlled data processing system including micro-instructions with data align control feature

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
FP780 Floating Point Accelerator Technical Description, Digital Equipment Corporation, 1978, pp. 2 37 to 2 41. *
FP780 Floating-Point Accelerator Technical Description, Digital Equipment Corporation, 1978, pp. 2-37 to 2-41.

Cited By (58)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0220684A2 (en) * 1985-10-25 1987-05-06 Hitachi, Ltd. Data processing system
EP0220684A3 (en) * 1985-10-25 1989-12-13 Hitachi, Ltd. Data processing system
EP0438961A2 (en) * 1990-01-24 1991-07-31 International Business Machines Corporation Hardware data string operation controller
EP0438961A3 (en) * 1990-01-24 1992-01-02 International Business Machines Corporation Hardware data string operation controller
US5168571A (en) * 1990-01-24 1992-12-01 International Business Machines Corporation System for aligning bytes of variable multi-bytes length operand based on alu byte length and a number of unprocessed byte data
US5410682A (en) * 1990-06-29 1995-04-25 Digital Equipment Corporation In-register data manipulation for unaligned byte write using data shift in reduced instruction set processor
US5367705A (en) * 1990-06-29 1994-11-22 Digital Equipment Corp. In-register data manipulation using data shift in reduced instruction set processor
US6954847B2 (en) 1992-03-31 2005-10-11 Transmeta Corporation System and method for translating non-native instructions to native instructions for processing on a host processor
US5438668A (en) * 1992-03-31 1995-08-01 Seiko Epson Corporation System and method for extraction, alignment and decoding of CISC instructions into a nano-instruction bucket for execution by a RISC computer
US7343473B2 (en) 1992-03-31 2008-03-11 Transmeta Corporation System and method for translating non-native instructions to native instructions for processing on a host processor
US6263423B1 (en) 1992-03-31 2001-07-17 Seiko Epson Corporation System and method for translating non-native instructions to native instructions for processing on a host processor
US7664935B2 (en) 1992-03-31 2010-02-16 Brett Coon System and method for translating non-native instructions to native instructions for processing on a host processor
US5546552A (en) * 1992-03-31 1996-08-13 Seiko Epson Corporation Method for translating non-native instructions to native instructions and combining them into a final bucket for processing on a host processor
US20080162880A1 (en) * 1992-03-31 2008-07-03 Transmeta Corporation System and Method for Translating Non-Native Instructions to Native Instructions for Processing on a Host Processor
US5983334A (en) * 1992-03-31 1999-11-09 Seiko Epson Corporation Superscalar microprocessor for out-of-order and concurrently executing at least two RISC instructions translating from in-order CISC instructions
US5619666A (en) * 1992-03-31 1997-04-08 Seiko Epson Corporation System for translating non-native instructions to native instructions and combining them into a final bucket for processing on a host processor
US20030084270A1 (en) * 1992-03-31 2003-05-01 Transmeta Corp. System and method for translating non-native instructions to native instructions for processing on a host processor
US7861069B2 (en) 1992-09-29 2010-12-28 Seiko-Epson Corporation System and method for handling load and/or store operations in a superscalar microprocessor
US6957320B2 (en) 1992-09-29 2005-10-18 Seiko Epson Corporation System and method for handling load and/or store operations in a superscalar microprocessor
US6965987B2 (en) 1992-09-29 2005-11-15 Seiko Epson Corporation System and method for handling load and/or store operations in a superscalar microprocessor
US20090217001A1 (en) * 1992-09-29 2009-08-27 Seiko Epson Corporation System and Method for Handling Load and/or Store Operations in a Superscalar Microprocessor
US6230254B1 (en) 1992-09-29 2001-05-08 Seiko Epson Corporation System and method for handling load and/or store operators in a superscalar microprocessor
US20070101106A1 (en) * 1992-09-29 2007-05-03 Senter Cheryl D System and method for handling load and/or store operations in a superscalar microprocessor
US8019975B2 (en) 1992-09-29 2011-09-13 Seiko-Epson Corporation System and method for handling load and/or store operations in a superscalar microprocessor
US6434693B1 (en) 1992-09-29 2002-08-13 Seiko Epson Corporation System and method for handling load and/or store operations in a superscalar microprocessor
US20020188829A1 (en) * 1992-09-29 2002-12-12 Senter Cheryl D. System and method for handling load and/or store operations in a superscalar microprocessor
US20030056089A1 (en) * 1992-09-29 2003-03-20 Seiko Epson Corporation System and method for handling load and/or store operations in a superscalar microprocessor
US7844797B2 (en) 1992-09-29 2010-11-30 Seiko Epson Corporation System and method for handling load and/or store operations in a superscalar microprocessor
US20040128487A1 (en) * 1992-09-29 2004-07-01 Seiko Epson Corporation System and method for handling load and/or store operations in a superscalar microprocessor
US7447876B2 (en) 1992-09-29 2008-11-04 Seiko Epson Corporation System and method for handling load and/or store operations in a superscalar microprocessor
US6735685B1 (en) 1992-09-29 2004-05-11 Seiko Epson Corporation System and method for handling load and/or store operations in a superscalar microprocessor
US20050283591A1 (en) * 1992-09-29 2005-12-22 Seiko Epson Corporation System and method for handling load and/or store operations in a superscalar microprocessor
EP0593073A1 (en) * 1992-10-16 1994-04-20 Matsushita Electric Industrial Co., Ltd. A processor incorporating shifters
US5528525A (en) * 1992-10-16 1996-06-18 Matsushita Electric Industrial Co., Ltd. Processor for determining shift counts based on input data
US5463746A (en) * 1992-10-30 1995-10-31 International Business Machines Corp. Data processing system having prediction by using an embedded guess bit of remapped and compressed opcodes
US5471598A (en) * 1993-10-18 1995-11-28 Cyrix Corporation Data dependency detection and handling in a microprocessor with write buffer
US6219773B1 (en) * 1993-10-18 2001-04-17 Via-Cyrix, Inc. System and method of retiring misaligned write operands from a write buffer
US5740398A (en) * 1993-10-18 1998-04-14 Cyrix Corporation Program order sequencing of data in a microprocessor with write buffer
US5584009A (en) * 1993-10-18 1996-12-10 Cyrix Corporation System and method of retiring store data from a write buffer
US5615402A (en) * 1993-10-18 1997-03-25 Cyrix Corporation Unified write buffer having information identifying whether the address belongs to a first write operand or a second write operand having an extra wide latch
US5673216A (en) * 1995-12-19 1997-09-30 International Business Machines Corporation Process and system for adding or subtracting symbols in any base without converting to a common base
US5912831A (en) * 1995-12-19 1999-06-15 International Business Machines Corporation Process and system for adding or substracting symbols in any base without converting to a common base
US6842850B2 (en) 1999-10-25 2005-01-11 Intel Corporation DSP data type matching for operation using multiple functional units
US7062637B2 (en) * 1999-10-25 2006-06-13 Intel Corporation DSP operations with permutation of vector complex data type operands
US6557096B1 (en) 1999-10-25 2003-04-29 Intel Corporation Processors with data typer and aligner selectively coupling data bits of data buses to adder and multiplier functional blocks to execute instructions with flexible data types
US20030172249A1 (en) * 1999-10-25 2003-09-11 Kumar Ganapathy Methods of performing DSP operations with complex data type operands
US20030154360A1 (en) * 1999-10-25 2003-08-14 Kumar Ganapathy Methods of performing DSP operations using flexible data type operands
US7318115B2 (en) 2000-01-31 2008-01-08 Intel Corporation IC memory complex with controller for clusters of memory blocks I/O multiplexed using collar logic
US7287148B2 (en) 2000-01-31 2007-10-23 Intel Corporation Unified shared pipeline allowing deactivation of RISC/DSP units for power saving
US7233166B2 (en) 2000-01-31 2007-06-19 Intel Corporation Bus state keepers
US20050076194A1 (en) * 2000-01-31 2005-04-07 Ruban Kanapathippillai Unified instruction pipeline for power reduction in a digital signal processor integrated circuit
US20040236896A1 (en) * 2000-01-31 2004-11-25 Ruban Kanapathippillai Memory with memory clusters for power reduction in an integrated circuit
US20030225984A1 (en) * 2000-08-10 2003-12-04 Terminus Technology Limited Associative memory having a mask function for use in a network router
WO2002019093A1 (en) * 2000-08-31 2002-03-07 Intel Corporation Method and apparatus for flexible data types
US20060047740A1 (en) * 2004-08-30 2006-03-02 Casio Computer Co., Ltd. Decimal computing apparatus, electronic device connectable decimal computing apparatus, arithmetic operation apparatus, arithmetic operation control apparatus, and program-recorded recording medium
US7716267B2 (en) * 2004-08-30 2010-05-11 Casio Computer Co., Ltd. Decimal computing apparatus, electronic device connectable decimal computing apparatus, arithmetic operation apparatus, arithmetic operation control apparatus, and program-recorded recording medium
US8316067B2 (en) 2004-08-30 2012-11-20 Casio Computer Co., Ltd. Decimal computing apparatus, electronic device connectable decimal computing apparatus, arithmetic operation apparatus, arithmetic operation control apparatus, and program-recorded recording medium
US20090204658A1 (en) * 2004-08-30 2009-08-13 Casio Computer Co., Ltd. Decimal computing apparatus, electronic device connectable decimal computing apparatus, arithmetic operation apparatus, arithmetic operation control apparatus, and program-recorded recording medium

Also Published As

Publication number Publication date
KR860000791B1 (en) 1986-06-25
JPS5743239A (en) 1982-03-11
JPH028327B2 (en) 1990-02-23
KR830006739A (en) 1983-10-06

Similar Documents

Publication Publication Date Title
Lee Programmable dsp architectures. i
US8447958B2 (en) Substituting portion of template instruction parameter with selected virtual instruction parameter
US4453212A (en) Extended address generating apparatus and method
US5844830A (en) Executing computer instrucrions by circuits having different latencies
US4839797A (en) Microprocessor compatible with any software represented by different types of instruction formats
US4725947A (en) Data processor with a branch target instruction storage
US4814976A (en) RISC computer with unaligned reference handling and method for the same
JP2992223B2 (en) Computer systems, methods instruction bit length compression, the instruction generating method, and computer system operation method
EP0239081B1 (en) Pipelined data processor capable of decoding and executing plural instructions in parallel
US5319757A (en) FORTH specific language microprocessor
GB1130270A (en) Data processing apparatus
US4707800A (en) Adder/substractor for variable length numbers
US4639886A (en) Arithmetic system having pipeline structure arithmetic means
US5487159A (en) System for processing shift, mask, and merge operations in one instruction
US5056004A (en) Program control system which simultaneously executes a program to be repeated and decrements repetition numbers
US4777587A (en) System for processing single-cycle branch instruction in a pipeline having relative, absolute, indirect and trap addresses
US4967326A (en) Microcomputer building block
EP0054888A2 (en) Data-processing system with main and buffer storage control
US4025771A (en) Pipe line high speed signal processor
US4740893A (en) Method for reducing the time for switching between programs
US6009451A (en) Method for generating barrel shifter result flags directly from input data
US3949370A (en) Programmable logic array control section for data processing system
US4733346A (en) Data processor with multiple register blocks
US3593306A (en) Apparatus for reducing memory fetches in program loops
KR100237985B1 (en) Method for executing speculative load instructions in high-performance processors

Legal Events

Date Code Title Description
AS Assignment

Owner name: HITACHI, LTD., 5-1, MARUNOUCHI 1-CHOME, CHUIODA-KU

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST.;ASSIGNORS:YANAGITA, TOMOATSU;NAGAFUJI, MOTONOBU;REEL/FRAME:003910/0952

Effective date: 19810804

STCF Information on status: patent grant

Free format text: PATENTED CASE

FPAY Fee payment

Year of fee payment: 4

FPAY Fee payment

Year of fee payment: 8

FPAY Fee payment

Year of fee payment: 12